Method for Detecting Foreign Objects in the Intake Duct of a Three-Dimensional LaserPoint Cloud Aircraft Engine Based on Curvature Mutation
In order to solve the problems of low accuracy and efficiency in manual inspection of aircraft engine intake ducts,a for-eign object detection method based on curvature mutation of three-dimensional laser point cloud is proposed for intake ducts.A voxel network-based point cloud data compression method is designed,and the curvature change of the compressed point cloud data is calcu-lated in the depth direction of the inlet.The iterative threshold method is used to calculate the dynamic threshold for segmenting the point cloud of curvature mutation,and the point cloud of foreign object is then identified by means of threshold segmentation for cur-vature mutation.The region growth method is used to cluster the discrete point cloud of foreign object into the whole foreign object.An analog test environment is constructed for the intake duct of aircraft engine,in which three different sizes of foreign objects are de-tected and located.The recognition rate for foreign object reaches 95.4％,and the locating accuracy for foreign object reaches 1.46 cm.The experimental results verify the accuracy and efficiency of the method.
万方数据
维普
